GPT-4o - In-Depth Overview

OpenAI · GPT-4o

Current

Flagship

Latest in family

Model ID: gpt-4o

Get all the details on GPT-4o, an AI model from OpenAI. This page covers its token limits, pricing structure, key capabilities such as streaming, structured_outputs, multimodal_input, available API code samples, and performance strengths.

Key Metrics

Input Limit

128K tokens

Output Limit

16.4K tokens

Input Cost

$2.50/1M

Output Cost

$10.00/1M

Sample API Code

from openai import OpenAI;client = OpenAI();response = client.chat.completions.create(model="gpt-4o",messages=[{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Hello!"}]);print(response.choices[0].message.content)

Required Libraries

openai

Benchmarks

Benchmark	Score	Source	Notes
lmarena text	1405	OpenLLM Leaderboard	Score for chatgpt-4o-latest-20250326
lmarena webdev	964	OpenLLM Leaderboard	Score for GPT-4o-2024-11-20
lmarena vision	1310	OpenLLM Leaderboard	Score for chatgpt-4o-latest-20250326
lmarena search	1000	OpenLLM Leaderboard	Score for api-gpt-4o-search
bfcl	72.08%	Vellum Leaderboard	-
aime 2024	13.4%	Vellum Leaderboard	-
gpqa	56.1%	Vellum Leaderboard	-
swe bench	31%	Vellum Leaderboard	-
math 500	60.3%	Vellum Leaderboard	-
alder polyglot	27.1%	Vellum Leaderboard	-
livebench global average	61.65	LiveBench Leaderboard	-
livebench reasoning average	48.81	LiveBench Leaderboard	-
livebench coding average	77.48	LiveBench Leaderboard	-
livebench mathematics average	55.72	LiveBench Leaderboard	-
livebench data analysis average	66.52	LiveBench Leaderboard	-
livebench language average	49.43	LiveBench Leaderboard	-
livebench if average	71.92	LiveBench Leaderboard	-

Notes

GPT-4o (“o” for “omni”) is OpenAI's versatile, high-intelligence flagship model. It accepts both text and image inputs, and produces text outputs (including Structured Outputs). It is the best model for most tasks, and is OpenAI's most capable model outside of its o-series models.